@InProceedings{nagpal-EtAl:2017:WNUT,
  author    = {Nagpal, Chirag  and  Miller, Kyle  and  Boecking, Benedikt  and  Dubrawski, Artur},
  title     = {An Entity Resolution Approach to Isolate Instances of Human Trafficking Online},
  booktitle = {Proceedings of the 3rd Workshop on Noisy User-generated Text},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {77--84},
  abstract  = {Human trafficking is a challenging law enforcement problem, and traces of
	victims of such activity manifest as ‘escort advertisements’ on various
	online forums. Given the large, heterogeneous and noisy structure of this data,
	building models to predict instances of trafficking is a convoluted task. In
	this paper we propose an entity resolution pipeline using a notion of proxy
	labels, in order to extract clusters from this data with prior history of human
	trafficking activity. We apply this pipeline to 5M records from backpage.com
	and report on the performance of this approach, challenges in terms of
	scalability, and some significant domain specific characteristics of our
	resolved entities.},
  url       = {http://www.aclweb.org/anthology/W17-4411}
}